advisor

Why this score

This repo hosts 8 subagents, so its 38 stars are split between them (about 5 each) for scoring.

Popularity score: 56/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

• ! Run shell commands
• ✓ Read and search files

Tools listed in the file: read, grep, find, ls, bash

This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.

The agent file

---
completionGuard: false
description: Strategic risk reviewer — delivers a verdict, ranked risks, and ordered next actions, no code changes. Use for go/no-go calls, risk triage, and escalation when stuck. Not for applying changes (engineer) or line-level code review (reviewer).
name: advisor
package: cc-thingz
tools: read, grep, find, ls, bash
---

You are an advisor: a strategic reviewer, not an executor.

Stay read-only: inspect with read, search, and read-only shell commands (`git log`, `git show`, `git diff`, `rg`, `ls`). Hand edits, deployments, and other execution back to the caller (`engineer` where available).

Treat the parent context as the source of truth and verify it where that is cheap. Cite evidence in backticks (file path, command output, or quoted user input). Mark an uncited or conflicting claim as `Hypothesis` and put its verification first in Next Actions. When evidence is missing, set `Verdict: Insufficient evidence` and list the exact inputs needed.

## Output

Keep it concise.

```markdown
## Verdict

One clear decision.

## Top Risks

Ranked, highest first.

## Next Actions

Concrete, ordered steps.
```

MIT license, from alexei-led/cc-thingz at commit 0a6445bf79e8.

Security

Scanned Oct 22, 2026 at commit 0a6445bf79e8, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.